Condition monitoring of wind turbines with the implementation of spatio-temporal graph neural network. (May 2023)

• Record Type: Journal Article
• Authors: Liu, Jiayang; Wang, Xiaosun; Xie, Fuqi; Wu, Shijing; Li, Deng
• Is Part Of: Engineering applications of artificial intelligence. Volume 121(2023)
• Publication Date: 2023-05
• Subjects: Wind turbine -- Condition monitoring -- Graph convolution -- Gated recurrent unit -- Spatio-temporal graph neural network -- Anomaly detection; Engineering -- Data processing -- Periodicals; Artificial intelligence -- Periodicals; Expert systems (Computer science) -- Periodicals; Ingénierie -- Informatique -- Périodiques; Intelligence artificielle -- Périodiques; Systèmes experts (Informatique) -- Périodiques; Artificial intelligence; Engineering -- Data processing; Expert systems (Computer science); Periodicals; 620.00285
• DOI: 10.1016/j.engappai.2023.106000
• Languages: English
• ISSNs: 0952-1976

Abstract

Abstract: Condition monitoring of wind turbines is critical to ensure their long-term stable operation. With the benefit of deep learning techniques, WTs' health status information can be mined more fully from supervisory control and data acquisition data. However, these deep learning-based condition monitoring methods have the following limitations. (1) They only can process regularly structured data, such as pictures, rather than general domains. (2) The spatial properties of wind turbines multi-sensor networks, i.e., connectivity and globality, are neglected. To overcome the above limitations, a new condition monitoring network named spatio-temporal graph neural network is proposed in this paper. First, the missing value supplement and the selection of variables with maximal information coefficient are applied. Meanwhile, the top-k nearest neighbors is employed to construct graphs. Then, a spatio-temporal block is established based on graph convolution networks and gated recurrent unit. By stacking multiple spatio-temporal blocks, the monitoring variables are estimated by feeding the learned features to the last prediction layer. Lastly, the proposed spatio-temporal graph neural network is validated using real wind farm supervisory control and data acquisition data. The experimental results indicate that the proposed method can detect the early abnormal operation efficiently and is superior to some existing methods, which can promote the utilization of renewable energy. Highlights: A novel spatio-temporal model is proposed for condition monitoring of wind turbine. The top-k nearest neighbors is used to construct graphs from time series data. Graph convolution is used to mine spatial features with connectivity and globality. The structure of graph convolution and GRU is used to fuse spatio-temporal features.